Hand Gesture Recognition Based on a Nonconvex Regularization

Jing Qin; Joshua Ashley; Biyun Xie

doi:10.1109/ICMA52036.2021.9512752

Hand Gesture Recognition Based on a Nonconvex Regularization

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low demands on the training data. Recently, nonconvex regularization techniques including the l1-2 regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based hand gesture recognition model based on the l1-2 regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on binary and gray-scale data sets have demonstrated the effectiveness of this method in identifying hand gestures.

Original language	English
Title of host publication	2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021
Pages	187-192
Number of pages	6
ISBN (Electronic)	9781665441001
DOIs	https://doi.org/10.1109/ICMA52036.2021.9512752
State	Published - Aug 8 2021
Event	18th IEEE International Conference on Mechatronics and Automation, ICMA 2021 - Takamatsu, Japan Duration: Aug 8 2021 → Aug 11 2021

Publication series

Name	2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021

Conference

Conference	18th IEEE International Conference on Mechatronics and Automation, ICMA 2021
Country/Territory	Japan
City	Takamatsu
Period	8/8/21 → 8/11/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

ACKNOWLEDGMENTS The research of Qin is supported by the NSF grant DMS-1941197 and the research of Ashley and Xie is supported by Woodrow W. Everett, Jr. SCEEE Development Fund in cooperation with the Southeastern Association of Electrical Engineering Department Heads.

Funders	Funder number
National Science Foundation (NSF)	DMS-1941197

Keywords

Hand gesture recognition
alternating direction method of multipliers
human-robot interaction
nonconvex regularization
sparsity

ASJC Scopus subject areas

Artificial Intelligence
Electrical and Electronic Engineering
Mechanical Engineering
Control and Optimization

Access to Document

10.1109/ICMA52036.2021.9512752

Cite this

@inproceedings{84fe91eab218407e93be06ba98436271,

title = "Hand Gesture Recognition Based on a Nonconvex Regularization",

abstract = "Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low demands on the training data. Recently, nonconvex regularization techniques including the l1-2 regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based hand gesture recognition model based on the l1-2 regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on binary and gray-scale data sets have demonstrated the effectiveness of this method in identifying hand gestures.",

keywords = "Hand gesture recognition, alternating direction method of multipliers, human-robot interaction, nonconvex regularization, sparsity",

author = "Jing Qin and Joshua Ashley and Biyun Xie",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE International Conference on Mechatronics and Automation, ICMA 2021 ; Conference date: 08-08-2021 Through 11-08-2021",

year = "2021",

month = aug,

day = "8",

doi = "10.1109/ICMA52036.2021.9512752",

language = "English",

series = "2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021",

pages = "187--192",

booktitle = "2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021",

}

Qin, J, Ashley, J & Xie, B 2021, Hand Gesture Recognition Based on a Nonconvex Regularization. in 2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021. 2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021, pp. 187-192, 18th IEEE International Conference on Mechatronics and Automation, ICMA 2021, Takamatsu, Japan, 8/8/21. https://doi.org/10.1109/ICMA52036.2021.9512752

Hand Gesture Recognition Based on a Nonconvex Regularization. / Qin, Jing; Ashley, Joshua; Xie, Biyun.
2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021. 2021. p. 187-192 (2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hand Gesture Recognition Based on a Nonconvex Regularization

AU - Qin, Jing

AU - Ashley, Joshua

AU - Xie, Biyun

PY - 2021/8/8

Y1 - 2021/8/8

N2 - Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low demands on the training data. Recently, nonconvex regularization techniques including the l1-2 regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based hand gesture recognition model based on the l1-2 regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on binary and gray-scale data sets have demonstrated the effectiveness of this method in identifying hand gestures.

AB - Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low demands on the training data. Recently, nonconvex regularization techniques including the l1-2 regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based hand gesture recognition model based on the l1-2 regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on binary and gray-scale data sets have demonstrated the effectiveness of this method in identifying hand gestures.

KW - Hand gesture recognition

KW - alternating direction method of multipliers

KW - human-robot interaction

KW - nonconvex regularization

KW - sparsity

UR - http://www.scopus.com/inward/record.url?scp=85115176782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115176782&partnerID=8YFLogxK

U2 - 10.1109/ICMA52036.2021.9512752

DO - 10.1109/ICMA52036.2021.9512752

M3 - Conference contribution

AN - SCOPUS:85115176782

T3 - 2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021

SP - 187

EP - 192

BT - 2021 IEEE International Conference on Mechatronics and Automation, ICMA 2021

T2 - 18th IEEE International Conference on Mechatronics and Automation, ICMA 2021

Y2 - 8 August 2021 through 11 August 2021

ER -

Hand Gesture Recognition Based on a Nonconvex Regularization

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this